Architecture map
How the repo is organized
Click systems in the graph to inspect responsibilities, important files, and nearby dependencies.
Architecture map
Use this map to orient around systems, dependencies, and files worth reading first.
Click a system in the map
Explore openclaw/openclaw by selecting services, gateways, clients, and data stores. Each node shows the files, responsibilities, and neighboring systems an agent should keep in scope.
Pan, zoom, and use the minimap to keep large repos navigable.
Sign up to turn selected graph context into repo-aware agent sessions.
Key systems
What an agent should understand first
Bootstrap node process, parse args, setup environment, enable compile cache
Load openclaw.json, auth profiles, channel setup, validate schema
Discover, manifest-parse, activate bundled and external plugins
Central inbound HTTP listener, message normalization, session routing
150+ channel adapters (Slack, Telegram, Discord, Signal, iMessage, WhatsApp, etc.)
SQLite-backed conversation history, session state, vector embeddings (lancedb)
Request batching, streaming, model invocation, tool call loop coordination
Route to 50+ LLM providers (OpenAI, Anthropic, Google, Mistral, local, etc.)
Evidence coverage
What this context is grounded in
Coverage
- Citations
- 7
- Findings
- 5
- Files discovered
- 10,381
- Architecture systems
- 14
- Architecture relationships
- 17
- Agent graph
- Agent graph entities
- 1,276
- Agent graph relationships
- 2,589